Komet: A Serverless Platform for Low-Earth Orbit Edge Services

TL;DR

Komet is introduced, a serverless platform for low-Earth orbit edge computing that integrates Function-as-a-Service compute with data replication, enabling on-demand elastic edge resource allocation and frequent service migration against satellite orbital trajectories to keep services deployed in the same geographic region.

Abstract

Low-Earth orbit satellite networks can provide global broadband Internet access using constellations of thousands of satellites. Integrating edge computing resources in such networks can enable global low-latency access to compute services, supporting end users in rural areas, remote industrial applications, or the IoT. To achieve this, resources must be carefully allocated to various services from multiple tenants. Moreover, applications must navigate the dynamic nature of satellite networks, where orbital mechanics necessitate frequent client hand-offs. Therefore, managing applications on the low-Earth orbit edge will require the right platform abstractions. We introduce Komet, a serverless platform for low-Earth orbit edge computing. Komet integrates Function-as-a-Service compute with data replication, enabling on-demand elastic edge resource allocation and frequent service migration against satellite orbital trajectories to keep services deployed in the same geographic region. We implement Komet as a proof-of-concept prototype and demonstrate how its abstractions can be used to build low-Earth orbit edge applications with high availability despite constant mobility. Further, we propose simple heuristics for service migration scheduling in different application scenarios and evaluate them in simulation based on our experiment traces, showing the trade-off between selecting an optimal satellite server at every instance and minimizing service migration frequency.

Figures (19)

• Figure 1: In its current deployment, the Starlink LEO satellite constellation comprises 4,409 satellites to achieve global coverage (screenshot from the Celestial emulation toolkit paper_pfandzelter2022_celestial). Lines between satellites indicate inter-satellite links (ISL).
• Figure 2: Container checkpoint, transfer, and restore times in our container migration experiment. It is obvious that the total migration time for a stateful container grows linearly with the amount of memory the container uses.
• Figure 3: Komet comprises a per-satellite FaaS compute platform and a replicated data store, hosting replicas of the application service on multiple satellites.
• Figure 4: Service Migration in Komet
• Figure 5: Our Komet prototype combines the tinyFaaS lightweight edge FaaS platform and FReD edge data management middleware with a central scheduling component. Functions are backed by replicated data and can be invoked by clients through an HTTP endpoint.